Researchers Backdoor Open AI Model to Steal Credentials in Coding Agents

(projectdiscovery.io)

3 points | by skpd 11 hours ago ago

2 comments

  • verdverm 11 hours ago ago

    1. these are older, weak models; newer or bigger models are more resistant to this

    2. don't give your agents access to credentials in the first place, build workflows around them instead

    example, I built a pr-review agent that has no credentials, no access to the internet, and no bash - it doesn't need these things to do a review

  • skpd 11 hours ago ago

    [dead]